@inproceedings{kozaeva-etal-2024-development,
title = "Development and Evaluation of a {G}erman Language Model for the Financial Domain",
author = "Kozaeva, Nata and
Hamotskyi, Serhii and
Hanig, Christian",
editor = "Chen, Chung-Chi and
Liu, Xiaomo and
Hahn, Udo and
Nourbakhsh, Armineh and
Ma, Zhiqiang and
Smiley, Charese and
Hoste, Veronique and
Das, Sanjiv Ranjan and
Li, Manling and
Ghassemi, Mohammad and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.finnlp-1.5",
pages = "40--49",
abstract = "Recent advancements in self-supervised pre-training of Language Models (LMs) have significantly improved their performance across a wide range of Natural Language Processing (NLP) tasks. Yet, the adaptation of these models to specialized domains remains a critical endeavor, as it enables the models to grasp domain-specific nuances, terminology, and patterns more effectively, thereby enhancing their utility in specialized contexts. This paper presents an in-depth investigation into the training and fine-tuning of German language models specifically for the financial sector. We construct various datasets for training and fine-tuning to examine the impact of different data construction strategies on the models{'} performance. Our study provides detailed insights into essential pre-processing steps, including text extraction from PDF documents and language identification, to evaluate their influence on the performance of the language models. Addressing the scarcity of resources in the German financial domain, we also introduce a German Text Classification benchmark dataset, aimed at fostering further research and development in this area. The performance of the trained models is evaluated on two domain-specific tasks, demonstrating that fine-tuning with domain-specific data improves model outcomes, even with limited amounts of domain-specific data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kozaeva-etal-2024-development">
<titleInfo>
<title>Development and Evaluation of a German Language Model for the Financial Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nata</namePart>
<namePart type="family">Kozaeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serhii</namePart>
<namePart type="family">Hamotskyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hanig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaomo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armineh</namePart>
<namePart type="family">Nourbakhsh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charese</namePart>
<namePart type="family">Smiley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjiv</namePart>
<namePart type="given">Ranjan</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Ghassemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hen-Hsen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in self-supervised pre-training of Language Models (LMs) have significantly improved their performance across a wide range of Natural Language Processing (NLP) tasks. Yet, the adaptation of these models to specialized domains remains a critical endeavor, as it enables the models to grasp domain-specific nuances, terminology, and patterns more effectively, thereby enhancing their utility in specialized contexts. This paper presents an in-depth investigation into the training and fine-tuning of German language models specifically for the financial sector. We construct various datasets for training and fine-tuning to examine the impact of different data construction strategies on the models’ performance. Our study provides detailed insights into essential pre-processing steps, including text extraction from PDF documents and language identification, to evaluate their influence on the performance of the language models. Addressing the scarcity of resources in the German financial domain, we also introduce a German Text Classification benchmark dataset, aimed at fostering further research and development in this area. The performance of the trained models is evaluated on two domain-specific tasks, demonstrating that fine-tuning with domain-specific data improves model outcomes, even with limited amounts of domain-specific data.</abstract>
<identifier type="citekey">kozaeva-etal-2024-development</identifier>
<location>
<url>https://aclanthology.org/2024.finnlp-1.5</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>40</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development and Evaluation of a German Language Model for the Financial Domain
%A Kozaeva, Nata
%A Hamotskyi, Serhii
%A Hanig, Christian
%Y Chen, Chung-Chi
%Y Liu, Xiaomo
%Y Hahn, Udo
%Y Nourbakhsh, Armineh
%Y Ma, Zhiqiang
%Y Smiley, Charese
%Y Hoste, Veronique
%Y Das, Sanjiv Ranjan
%Y Li, Manling
%Y Ghassemi, Mohammad
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%S Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing
%D 2024
%8 May
%I Association for Computational Linguistics
%C Torino, Italia
%F kozaeva-etal-2024-development
%X Recent advancements in self-supervised pre-training of Language Models (LMs) have significantly improved their performance across a wide range of Natural Language Processing (NLP) tasks. Yet, the adaptation of these models to specialized domains remains a critical endeavor, as it enables the models to grasp domain-specific nuances, terminology, and patterns more effectively, thereby enhancing their utility in specialized contexts. This paper presents an in-depth investigation into the training and fine-tuning of German language models specifically for the financial sector. We construct various datasets for training and fine-tuning to examine the impact of different data construction strategies on the models’ performance. Our study provides detailed insights into essential pre-processing steps, including text extraction from PDF documents and language identification, to evaluate their influence on the performance of the language models. Addressing the scarcity of resources in the German financial domain, we also introduce a German Text Classification benchmark dataset, aimed at fostering further research and development in this area. The performance of the trained models is evaluated on two domain-specific tasks, demonstrating that fine-tuning with domain-specific data improves model outcomes, even with limited amounts of domain-specific data.
%U https://aclanthology.org/2024.finnlp-1.5
%P 40-49
Markdown (Informal)
[Development and Evaluation of a German Language Model for the Financial Domain](https://aclanthology.org/2024.finnlp-1.5) (Kozaeva et al., FinNLP 2024)
ACL
- Nata Kozaeva, Serhii Hamotskyi, and Christian Hanig. 2024. Development and Evaluation of a German Language Model for the Financial Domain. In Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing, pages 40–49, Torino, Italia. Association for Computational Linguistics.